© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 26895
    Prev
    Next
    INDEX
    Explanations

    mentions of numerical limits in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.15
    0.9%
    408
    +0.12
    0.7%
    217
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    381
    +0.15
    0.01
    355
    +0.12
    0.01
    408
    +0.11
    0.01
    Negative Logits
    nexpected
    -1.85
    )](#
    -1.69
    LLOW
    -1.68
    ller
    -1.63
    "))
    -1.58
    oretical
    -1.56
    ))$
    -1.53
    |^{
    -1.52
    ]>
    -1.51
     glance
    -1.49
    POSITIVE LOGITS
    cule
    2.01
    ional
    1.92
    ions
    1.78
    endi
    1.76
    ais
    1.74
     positions
    1.72
    enses
    1.66
     (“
    1.64
    illo
    1.63
     amounts
    1.60
    Activations Density 0.015%

    No Known Activations